Listing of Current Work in Progress:
Printed Chinese Character Recognition
Using a mix of distortion modeling, statistical analysis, and neural network training, we are currently working on an omnifont Chinese character classifier. To date, a working model and GUI front-end have been created that operates using a generic classifier. Currently, the available classifiers are all variants of a single font classifier for the simplified SongTi character set. A SunOS 4.x demo and a technical paper can be grabbed via the above link.
Table Decomposition
Building on some of the tools developed by the lab and outside the lab, including a fast bi-level image convolution algorithm, cellular image processing tools, and an image vectorizer, (bitmap to raster converter,) we are building tools for Boeing Corp. that will transform a printed/typed table of data back into a usable ASCII form. Traditional OCR methods perform poorly because of the horizontal and vertical lines separating table cells, which often overlap with part of the cell data. No demo is available.
Image Feature Access Algorithms
We have implemented an algorithm that will allow dynamic insertion and deletion of features (each of which occopies a particular rectangular region) in O(log n) time, exact match queries in O(log n) time, containment searches in O((n^3 * (log n)) ^ (1/4) + k), and intersection searches in O((n^3 * (log n)) ^ (1/4) + k), where k is the number of objects returned.
Technical Drawing and Figure Decomposition
Table decomposition is really an adjunct of the more general task of technical drawing and figure decomposition. We are constantly building and refining the tools that allow us to do any component part of these tasks. Included is the extraction, storage, and access of generic image features. Currently, one long-term goal of the lab is a project we call Feature Center, which defines primitives and access operators for generic feature objects. The idea is to create a standard toolbox and API that is general enough to be used for all types of features, thus allowing an application programmer to easily plug in and use the particular feature extraction engines he might need for a particular application. For example, multiple OCR engines could easily be tried on a particular problem. The only thing to write would be the glue between the particular engine and Feature Center. And of course, once that is written, the engine can be used over repeatedly without having to be written again. Furthermore, it simplifies the coding process by standardizing feature access methods.
Intelligent Frame Buffer
This is a project that involves a ring of networked computers, each of which has the ability to write to the same screen
in real time
. In essence, the video signal is pumped around the ring at the same speed as the screen refresh rate. Each member of the ring reads the incoming signal and compares it to its local video buffer. Both the local and the incoming signal contain a priority setting for each pixel, in essence, a z-channel. If the local buffer has higher priority than the incoming signal, the local buffer supercedes it on the outgoing signal. All of this is done in hardware. Each local CPU only has to "draw" what it wants as if it were a standard memory-mapped local screen.
This page has been accessed
times since June 20, 1995.